一种高噪声低照度图像的隐藏特征修复算法

A hidden feature restoration algorithm for high noise and low illumination images

当前的图像隐藏特征修复算法的特征融合过程为单次迭代,且为根据光照情况建立暗适应函数,导致低照度图像隐藏特征修复结果存在失真问题,图像噪声也偏高。为此,提出一种基于交替优化的低照度图像隐藏特征修复算法。模拟低光照对图像环境的自动应变能力,并根据光照情况设计暗适应函数,对隐藏特征像素点实现边缘拉伸及中值滤波操作,提取处理后的隐藏特征分量数值,建立非线性映射函数,交替优化融合特征信息,实现低照度图像隐藏特征的修复。仿真结果证明,所提方法可以有效提高色彩饱和度,并且不易出现失真、特征丢失以及噪声现象,在最大程度上保证原始图像的自身特征属性,实现合理有效的隐藏特征修复。

Due to single iteration and dark adaptation function, the traditional image hiding feature restoration algorithm has a low illumination image hiding feature, distortion restoration effect and high image noise. Therefore, we report a low illumination image hidden feature restoration algorithm based on alternating optimization. Meanwhile, based on the illumination, the dark adaptation function was designed. The hidden feature pixels were stretched by edges and median filtered. The processed hidden feature component values were extracted to found a nonlinear mapping function, and the fusion feature information was optimized alternately, thus completing the restoration of hidden features of low illumination images. The simulation results show that this method improves color saturation and reduces noise, distortion, and feature loss.